itsm-email-recommendation
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its handling of untrusted data from ServiceNow incident records.
- Ingestion points: The skill reads from the
incidenttable (Step 1),sys_emailhistory (Step 2), andsys_journal_fieldwork notes (Step 3) in SKILL.md. - Boundary markers: No delimiters or instructions to ignore embedded commands are present in the prompt templates shown in Step 6.
- Capability inventory: The skill utilizes
SN-Update-Record,SN-Add-Work-Notes, and the high-privilegeSN-Execute-Background-Scripttool in SKILL.md. - Sanitization: There is no documented validation or filtering of the content retrieved from ServiceNow before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill uses
SN-Execute-Background-Scriptto perform server-side operations on the ServiceNow instance. - Evidence: Step 5 and Example 3 in SKILL.md provide server-side JavaScript templates used to query the ServiceNow database and process records.
- Context: This functionality requires administrative or specialized developer privileges on the target platform and allows for the execution of arbitrary JavaScript within the ServiceNow server context.
Audit Metadata